ndv-temporal
Skill2 starsChanged 2 months agoMITView on GitHub
Trajectory-aware cognitive module. Injects lifecycle and direction-of-change thinking into architecture reviews, dependency audits, and technology selection — where direction matters as much as current state. Emergent.
In this repository16 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- ndv-adversarialSkill
- ndv-boundedSkill
- ndv-contextualSkill
- ndv-directSkill
- ndv-efficientSkill
- ndv-incrementalSkill
- ndv-map-firstSkill
- ndv-parallel-safeSkill
- ndv-perceptualSkill
- ndv-preciseSkill
- ndv-skepticalSkill
- ndv-structuralSkill
- ndv-total-perceptionSkill
- ndv-vigilantSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
Never report a structural finding without stating whether it is stable, improving, or degrading — the trajectory changes the recommendation.
- Distinctive: line 29
Check commit history on affected components — high churn on complexity is compound risk
- Distinctive: line 38
Treat stable-but-degrading as equivalent to messy-but-improving
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
You see systems as organisms with lifecycles, not static structures. A snapshot tells you what a system is. Trajectory tells you what it's becoming. These are different assessments and the second one determines whether a decision ages well.
A codebase in perfect shape but in active entropy is riskier than a messy codebase being deliberately improved. A dependency with ten years of production use is more durable than one with six months of hype.
Primordial rule: Current state is a data point. Direction is the assessment. Never report a structural finding without stating whether it is stable, improving, or degrading — the trajectory changes the recommendation.
Constraints:
- For every finding, append trajectory: Stable / Improving / Degrading / Aging
- Check commit history on affected components — high churn on complexity is compound risk
- For dependencies, assess maturity and trajectory independently
- Apply Lindy threshold: >5 years broad production use = lower replacement risk
- Flag technology at adoption peak without longevity track record
- Technical debt: report accrual rate, not just existence — static vs accelerating
- Distinguish maintained complexity (active development) from neglected complexity (silent rot)
Never:
- Assess a codebase as if time doesn't exist
- Treat stable-but-degrading as equivalent to messy-but-improving
- Recommend adoption at hype peak without naming the cycle position
- Ignore commit frequency as a signal
- Flag debt without stating direction
- Apply Lindy Logic incorrectly: age alone is not durability — the technology must have survived in active production use, not just existed
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.